{"id":"https://openalex.org/W4391021728","doi":"https://doi.org/10.1109/asru57964.2023.10389698","title":"LV-CTC: Non-Autoregressive ASR With CTC and Latent Variable Models","display_name":"LV-CTC: Non-Autoregressive ASR With CTC and Latent Variable Models","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021728","doi":"https://doi.org/10.1109/asru57964.2023.10389698"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040732498","display_name":"Yuya Fujita","orcid":"https://orcid.org/0000-0001-8155-6040"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["LY Corporation,Tokyo,Japan","LY Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LY Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LY Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,PA,USA","Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University,PA,USA","Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059612504","display_name":"Takashi Maekaku","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Maekaku","raw_affiliation_strings":["LY Corporation,Tokyo,Japan","LY Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LY Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LY Corporation, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.8197591304779053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7267041206359863},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7249347567558289},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.614874005317688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5642255544662476},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5520126819610596},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5080687999725342},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4925261437892914},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.46326401829719543},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42438405752182007},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3248523473739624},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08909222483634949},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07402929663658142}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8197591304779053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267041206359863},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7249347567558289},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.614874005317688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5642255544662476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5520126819610596},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5080687999725342},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4925261437892914},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.46326401829719543},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42438405752182007},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3248523473739624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08909222483634949},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07402929663658142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2600687292","https://openalex.org/W2766219058","https://openalex.org/W2771976988","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963434219","https://openalex.org/W2964110616","https://openalex.org/W2972389417","https://openalex.org/W2972818416","https://openalex.org/W2988975212","https://openalex.org/W2996843693","https://openalex.org/W3007328579","https://openalex.org/W3096160024","https://openalex.org/W3096318498","https://openalex.org/W3097777922","https://openalex.org/W3112157188","https://openalex.org/W3162249256","https://openalex.org/W3162431424","https://openalex.org/W3162899666","https://openalex.org/W3163793923","https://openalex.org/W3169714379","https://openalex.org/W3175665465","https://openalex.org/W3196500669","https://openalex.org/W3197140813","https://openalex.org/W3197304116","https://openalex.org/W3198116002","https://openalex.org/W3205920203","https://openalex.org/W3206573929","https://openalex.org/W4210663600","https://openalex.org/W4224919446","https://openalex.org/W4225644313","https://openalex.org/W4319862255","https://openalex.org/W4388017359","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6640963894","https://openalex.org/W6691770337","https://openalex.org/W6739901393","https://openalex.org/W6746208923","https://openalex.org/W6748381668","https://openalex.org/W6774835902"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2053269318","https://openalex.org/W2546021431","https://openalex.org/W2581127593","https://openalex.org/W2073435713","https://openalex.org/W2962930338","https://openalex.org/W4302439501"],"abstract_inverted_index":{"Non-autoregressive":[0],"(NAR)":[1],"models":[2,62,138],"for":[3,78],"automatic":[4],"speech":[5],"recognition":[6,119,131],"(ASR)":[7],"aim":[8],"to":[9,91,101],"achieve":[10],"high":[11],"accuracy":[12,120,132],"and":[13,51,75],"fast":[14],"inference":[15,141],"by":[16],"simplifying":[17],"the":[18,33,60,64,84,95,117,126,129],"autoregressive":[19],"(AR)":[20],"generation":[21],"process":[22],"of":[23,32,59,113],"conventional":[24],"models.":[25,40,124],"Connectionist":[26],"temporal":[27],"classification":[28],"(CTC)":[29],"is":[30,57,89,133],"one":[31,58],"key":[34],"techniques":[35],"used":[36],"in":[37,63],"NAR":[38,123],"ASR":[39,79],"In":[41,83],"this":[42],"paper,":[43],"we":[44],"propose":[45],"a":[46,52,109],"new":[47,71],"model":[48],"combining":[49],"CTC":[50,87],"latent":[53,96],"variable":[54],"model,":[55,86],"which":[56],"state-of-the-art":[61],"neural":[65,72],"machine":[66],"translation":[67],"research":[68],"field.":[69],"A":[70],"network":[73],"architecture":[74],"formulation":[76],"specialized":[77],"application":[80],"are":[81,99],"introduced.":[82],"proposed":[85],"alignment":[88],"assumed":[90],"be":[92],"dependent":[93],"on":[94,108],"variables":[97],"that":[98],"expected":[100],"capture":[102],"dependencies":[103],"between":[104],"tokens.":[105],"Experimental":[106],"results":[107],"100":[110],"hours":[111],"subset":[112],"Librispeech":[114],"corpus":[115],"showed":[116],"best":[118,130],"among":[121],"CTC-based":[122],"On":[125],"TED-LIUM2":[127],"corpus,":[128],"achieved":[134],"including":[135],"AR":[136],"E2E":[137],"with":[139],"faster":[140],"speed.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}